Papers › Video Joint Modelling Based on Hierarchical Transformer for Co-summarization

Video Joint Modelling Based on Hierarchical Transformer for Co-summarization

27 Dec 2021arXiv:2112.13478archive 2025-07-28

Li Haopeng, Ke Qiuhong, Gong Mingming, Zhang Rui

Video summarization aims to automatically generate a summary (storyboard or video skim) of a video, which can facilitate large-scale video retrieval and browsing. Most of the existing methods perform video summarization on individual videos, which neglects the correlations among similar videos. Such correlations, however, are also informative for video understanding and video summarization. To address this limitation, we propose Video Joint Modelling based on Hierarchical Transformer (VJMHT) for co-summarization, which takes into consideration the semantic dependencies across videos. Specifically, VJMHT consists of two layers of Transformer: the first layer extracts semantic representation from individual shots of similar videos, while the second layer performs shot-level video joint modelling to aggregate cross-video semantic information. By this means, complete cross-video high-level patterns are explicitly modelled and learned for the summarization of individual videos. Moreover, Transformer-based video representation reconstruction is introduced to maximize the high-level similarity between the summary and the original video. Extensive experiments are conducted to verify the effectiveness of the proposed modules and the superiority of VJMHT in terms of F-measure and rank-based evaluation.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

HopLee6/VJMHT-PyTorch officialmentioned on GitHubpytorch report
thswodnjs3/CSTA mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

RetrievalSupervised Video SummarizationVideo RetrievalVideo SummarizationVideo Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Supervised Video Summarization SumMe VJMHT F1-score (Augmented) 51.7 #11 of 21 Archive leaderboard report
Supervised Video Summarization SumMe VJMHT F1-score (Canonical) 50.6 #11 of 21 Archive leaderboard report
Supervised Video Summarization SumMe VJMHT Kendall's Tau 0.106 #11 of 21 Archive leaderboard report
Supervised Video Summarization SumMe VJMHT Spearman's Rho 0.108 #11 of 21 Archive leaderboard report
Supervised Video Summarization TvSum VJMHT F1-score (Augmented) 61.9 #14 of 21 Archive leaderboard report
Supervised Video Summarization TvSum VJMHT F1-score (Canonical) 60.9 #14 of 21 Archive leaderboard report
Supervised Video Summarization TvSum VJMHT Kendall's Tau 0.097 #14 of 21 Archive leaderboard report
Supervised Video Summarization TvSum VJMHT Spearman's Rho 0.105 #14 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections